SUMMARY

• 8+ years of Data Science experience which includes Machine Learning, Statistical Analysis, Financial Data Analytics, Data Visualization, Natural Language Processing, Deep Learning, Data Operations and Business Intelligence.
• Highly proficient in Python data science libraries such as Numpy, Pandas, Matplotlib, Seaborn, NLTK and Scikit - learn etc.
• A deep understanding of Supervised / Unsupervised Machine Learning and statistical techniques such as Linear Regression, Logistic Regression, KNN, Support Vector Machines (SVM), Decision Trees and Random Forests, Naïve Bayes Classification, Principal Component Analysis (PCA), Recommender System, K Means Clustering etc. using Python and its Data Science libraries.
• Comfortable with statistical concepts such as Hypothesis test, ANOVA, T tests, Correlation, A/B test, Experimental Design, Time Series etc.
• Worked with other statistical tools like R, STATA, SPSS, SAS, MATLAB, and Excel to develop predictive models.
• Worked with Tableau, Excel, Python (Matplotlib, Seaborn), ArcGIS to create dashboards and visualizations.
• Highly experienced in in Credit Risk Management, Consumer Finance, Corporate Banking, Project Finance, Public Private Partnership, M&A, Private Equity and various financial products and services.
• Highly skilled in Financial Modeling, Transaction Advisory, Financial and Economic Analysis, Equity Research, Report Writing, and Project Management.
• Involved in deal origination, structuring, arranging and financing PPP, renewable energy and energy efficient projects.
• Closely worked with Relationship Managers, Financial Analysts and Economists team for Deal Origination and Credit Appraisal preparation.
• Expertise in transforming business requirements into analytical models, designing algorithms, building Financial Models, developing datamining and reporting solutions that scales across massive volume of structured and unstructured data.
• Familiar with Object Oriented Programming (OOP) concepts using Python.
• Creative and innovative in looking at problems by using data mining approaches on the set of information available.
• Experience on creating the appropriate algorithm to discover patterns, validate their findings using an experimental and iterative approach.
• Applied advanced statistical and predictive modeling techniques to build, maintain, and improve on multiple real-time decision systems.
• Good understanding on data preparation techniques.
• Hands on experience in business understanding, data understanding, and preparation of large databases.
• Experience in working with Relational Database Management System (RDBMS) with advanced SQL programming skills.
• Good understanding on mapping and tracing data from system to system in order to establish data hierarchy and lineage.
• Used Data Lineage and reverse engineering as a way to track back errors in data till the data source.
• Strong experience in interacting with stakeholders/customers, gathering requirements through interviews, workshops, and existing system documentation or procedures, defining business processes, identifying and analyzing risks using appropriate templates and analysis tools.

TECHNICAL SKILLS

Coding: Python (Numpy, Pandas, Scikit-Learn, NLTK), STATA, MATLAB, SAS, MySQL, R, Minitab etc.

Visualization: Tableau, Python (Matplotlib, Seaborn), R, MS Excel, Microsoft Power BI.

Microsoft Office Suite: MS Excel (VBA, MACROS, Pie Chart, Bar Chart, Pivot Table), MS Word, MS PowerPoint.

IDE: Anaconda, R-Studio, Visual Studio Code, Jupyter Notebook etc.

Machine Learning: Linear Regression, Logistic Regression, Time Series, SVM, K Means Clustering, KNN, Naïve Bayes Classification, Principal Component Analysis, Recommender System, NLP etc.

PROFESSIONAL EXPERIENCE

Confidential - Richmond, VA

Data Scientist

Responsibilities:

• Developing code and algorithms to explore, extract, clean, integrate and prepare data from various sources for fitting into models and Business Intelligence (BI).
• Working collaboratively with other data scientists and team members to develop statistical or machine learning models for a variety of applications across the bank.
• Creating advanced BI dashboards and visualizations with the help of MS Excel Pie Chart, Bar Chart, Pivot Table, Tableau, Python (Matplotlib, Seaborn) and Microsoft Power BI to present complex concepts to diverse audience across the bank.
• Formulating loan default prediction strategies using AI/Machine Learning for the bank.
• Developing and enhancing predictive models using advanced statistical and Machine Learning techniques such as OLS & Logistic regression, decision trees/forests, clustering, and recommender system etc. for fraud detection, loan default prediction, cross product selling for the Confidential auto finance.
• Applied Data Mining techniques to understand the sales pattern, classify the consumers, associating consumer attributes, detecting outliers, clustering and predicting auto sales and auto credit risk.
• Applied machine learning, time series and other statistical techniques using Python, R, SAS, MATLAB to forecast sales volumes, consumer preferences, auto credit risk etc.
• Built deployable machine learning models to support cross sell, sentiment analysis and superior customer experience.
• Designed and performed controlled experiments to assess the business value of new models.
• Collected and analyze data from company databases to drive optimization and improvement of product development, marketing techniques and business strategies.
• Presented insights and recommendations to Senior Management to drive change.

Environment: Python (Numpy, Pandas, Scikit-Learn, Matplotlib, Seaborn, SciPy), MySQL, Web Scraping, Collaborative filtering, Clustering, PCA, Various classification and recommendation algorithms, Tableau, R, MS Excel (VBA, MACROS, Count IF, SUM IF, Pie Chart, Bar Chart), Visual Studio Code, Jupyter Notebook etc.

Confidential

Manager Data Science

Responsibilities:

• Involved in the origination, structuring and analyzing a pipeline of potential private sector infrastructure projects and screen investment opportunities in Public Private Partnership (PPP), Public and Private Infrastructure, Renewable Energy and Energy Efficient Projects.
• Involved in all phases of data analysis which includes data collection, data cleaning, data mining, developing models & visualizations for investment analysis and due diligence purpose.
• Analyzed and developed complex financial models leveraging Bloomberg and other data sources.
• Developed and used various machine learning algorithms such as OLS, Logistic regression, KNN, SVM and K Means Clustering Algorithms to build predictive models for sales and revenue as an input for Financial Modeling.
• Used unsupervised machine learning such as K-means clustering, Hierarchical clustering, Linear Discriminant Analysis, Dimensionality Reduction techniques, PCA for customer segmentation and Geographical Plotting and Mapping for visualization.
• Used Recommender System to offer relevant suggestions to the clients as an advisory development initiative.
• Used predictive models and machine learning algorithms to increase and optimize customer experiences, revenue generation, ad targeting and other business outcomes for the clients.
• Performed Boosting method on predicted model for the improve efficiency of the model.
• Performed complex data mining and visualization using SQL, Tableau, Python (Matplotlib, Seaborn), Excel etc.
• Collaborated with business & product teams to understand the business problems and goals, developed predictive modeling, statistical analysis, data reports and performance metrics to solve the problems.
• Part of the team which managed investment portfolio of $100 Million+ in power, energy, healthcare & ICT sector through client outreach, marketing and deal screening.

Environment: Python (Numpy, Pandas, Scikit-Learn, Matplotlib, Seaborn, SciPy), STATA, MySQL, MS Excel (VBA, MACROS, Count IF, SUM IF, Pie Chart, Bar Chart), Tableau, Spark, Apache Spark, Hive, HDFS, Tableau, DynamoDB, Mongo DB, SQL Server etc.

Confidential

Junior Data Scientist

Responsibilities:

• Initiated IPO & RPO related research process which includes financial modeling, forecasting, valuation etc.
• Conducted regression analyses (VAR & SVAR) between company stock prices and macro-economic factors for more accurate prediction and performance.
• Utilized web scraping techniques to extract and organize market data.
• Used statistical and machine learning techniques for forecasting indexes and classifying stocks in a given portfolio.
• Designed and developed reporting dashboards and multidimensional data models using Excel and Tableau.
• Executed complex queries in SQL to filter, summarize and automate data extraction.
• Applied machine learning and AI techniques to perform market research and analysis.
• Part of the team which managed issuance of $25 M Zero Coupon Bond and Coupon bond as a part of Basel-II capital requirements for leading private commercial banks in Bangladesh.

Environment: Python (Numpy, Pandas, Scikit-Learn, Matplotlib, Seaborn, SciPy), MS Excel (VBA, MACROS, Count IF, SUM IF, Pie Chart, Bar Chart), STATA, SAS, SQL, Tableau, ArcGIS etc.